Sciweavers

573 search results - page 71 / 115
» Evolutionary functional testing of continuous control system...
Sort
View
NIPS
1996
14 years 11 months ago
Multidimensional Triangulation and Interpolation for Reinforcement Learning
Dynamic Programming, Q-learning and other discrete Markov Decision Process solvers can be applied to continuous d-dimensional state-spaces by quantizing the state space into an arr...
Scott Davies
GECCO
2005
Springer
138views Optimization» more  GECCO 2005»
15 years 3 months ago
Artificial immune system for solving generalized geometric problems: a preliminary results
Generalized geometric programming (GGP) is an optimization method in which the objective function and constraints are nonconvex functions. Thus, a GGP problem includes multiple lo...
Jui-Yu Wu, Yun-Kung Chung
CG
2002
Springer
14 years 9 months ago
Gentropy: evolving 2D textures
Gentropy is a genetic programming system that evolves two-dimensional procedural textures. It synthesizes textures by combining mathematical and image manipulation functions into ...
Andrea L. Wiens, Brian J. Ross
NECO
2007
115views more  NECO 2007»
14 years 9 months ago
Training Recurrent Networks by Evolino
In recent years, gradient-based LSTM recurrent neural networks (RNNs) solved many previously RNN-unlearnable tasks. Sometimes, however, gradient information is of little use for t...
Jürgen Schmidhuber, Daan Wierstra, Matteo Gag...
CDC
2009
IEEE
116views Control Systems» more  CDC 2009»
15 years 1 months ago
On the linear-exponential filtering problem for general Gaussian processes
The explicit solution of the filtering problem with exponential criteria for a general Gaussian signal is obtained through an approach which is based on a conditional Cameron-Mart...
Marina L. Kleptsyna, Alain Le Breton, Michel Viot